© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 182632
    Prev
    Next
    INDEX
    Explanations

    aptitude tests

    np_acts-logits-general · gemini-2.5-flash-lite

    state and law

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Psychic
    0.53
    社交
    0.48
    社会的
    0.48
     Andrzej
    0.46
    სი
    0.46
     և
    0.46
    νό
    0.45
    节省
    0.44
    社会
    0.44
    媺
    0.44
    POSITIVE LOGITS
    bai
    0.46
     yard
    0.45
    drinks
    0.45
    confined
    0.44
    acids
    0.44
     அவனே
    0.44
    records
    0.43
    cucumber
    0.43
    Джек
    0.42
    result
    0.42
    Activations Density 0.002%

    No Known Activations